All Claude Code modsDominic-DK/harnist
lens
Langfuse-lite for Claude Code: records load, usage, cache hits, turn scores and cost per session; /lens pane and prompt line; lens-review skill
lens reaches L2 (writes or runs) and passed claude plugin validate with warnings.
- Events hooked: 16
- API methods referenced: 23
- Access from classified calls: L2, writes or runs: writes files, drives Claude, reads files, reads env vars, reads mod state, persists state, draws
- Reads mod state: the scan does not record whose state, so this does not show that it reads another mod’s values
- Static scan, not a runtime test
Install hint
/plugin install lens --marketplace Dominic-DK/harnistFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.
Access
L2 Writes or runswrites files, drives Claude, reads files, reads env vars, reads mod state, persists state, drawsValidation
Passed with warningsListed under Prompt cache mods for Claude Code, Context and usage meters for Claude Code.
View the source on GitHub Back to the list
What the scan recorded
- Observed events
- mcp__lens__report calls, the system prompt, every skill, subagent spawns, every tool call, compaction
- Hooks
tool.call {tool=mcp__lens__report}, session.start, session.end, command.run {command=lens}, prompt.section, prompt.compose, prompt.attachment, skill.prompt, agent.spawn, tool.check, tool.call, turn.start, session.compact, turn.step, turn.complete, session.measure, ui.render {component=PromptHint}, ui.render {component=Pane, requestId=lens}- API calls
$.agent.list, $.clock.every, $.command.register, $.env.get, $.fs.exists, $.fs.list, $.fs.read, $.fs.write, $.prompt.submit, $.session.cwd, $.session.id, $.session.model, $.session.turns, $.session.usage, $.session.version, $.state.get, $.state.set, $.store.get, $.store.set, $.tool.register, $.ui.log, $.ui.open, $.ui.resolve- Validation
- Passed with warnings
- Scanned revision
b09614cab87c- Marketplace passed
- harnist
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. What a mod can access and how the scan works.
More from Dominic-DK/harnist
- runtimeharnist runtime mod: per-role subagent loading: trims skill list, MCP notes and CLAUDE.md per subagent type,…
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/Dominic-DK--harnist--lens/)
[](https://mods.aidojo.si/mods/Dominic-DK--harnist--lens/)